An improved double-population artificial bee colony algorithm based on heterogeneous comprehensive learning

The artificial bee colony (ABC) algorithm is one of the popular swarm intelligence algorithms that is inspired by the forging behavior of honeybee colonies. To improve the convergence precision of the ABC algorithm, accelerate the search speed of finding the best solution and control the balance between exploration and exploitation, we propose an improved double-population ABC algorithm based on heterogeneous comprehensive learning (HCLIABC). In this algorithm, the swarm is divided into exploration-subpopulation named group 1 and exploitation-subpopulation named group 2. Illuminated by particle swarm optimization (PSO), the food source will be updated on all dimensions rather than on a randomly selected dimension. Meanwhile HCL strategy is used to generate the exemplars for two subpopulations. In addition, opposition-based learning is used to improve the quality of initial swarm, and multiplicative weight update method is used to update the selection probability of the double-population in employed bees phase. To evaluate the remarkable performance of the improved algorithm, we conduct comparative experiments of 18 unimodal, multimodal, and rotated benchmark functions on dimensions 30 and 100. Computational results demonstrate that HCLIABC can effectively prevent premature convergence and produce competitive optimization precision and convergence speed compared with several popular and classic DE, PSO and ABC variants.